Skip to content
conftrace_

gradient-based analysis

7 papers

Explore in graph

Co-occurring keywords · papers mentioning both

neural network (2) large language model (2) gradient analysis (2) model interpretability (2) attention mechanism (2) language model explanation (1) path integration (1) neuron activation modulation (1) activation difference analysis (1) natural language processing model (1)

Papers

Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders EMNLP 2025 Neuron Activation Modulation for Text Style Transfer: Guiding Large Language Models ACL 2025 Causal Intersectionality and Dual Form of Gradient Descent for Multimodal Analysis: A Case Study on Hateful Memes COLING 2024 Improving LLM Attributions with Randomized Path-Integration EMNLP 2024 Not Everything is All You Need: Toward Low-Redundant Optimization for Large Language Model Alignment EMNLP 2024 Gradient-based Analysis of NLP Models is Manipulable EMNLP 2020 Is Attention Interpretable? ACL 2019